Choose Auto, TokenLab Verified, or Official for each request, with prices shown up front. See what's new

Models

Compare models by price, context, and capability. The Official price is the model maker's published price.

Alibaba Cloud

ModelContextMax outputOfficial priceVerified priceDiscount
qwen3-coder-flashCodePrompt CacheSupports prompt caching
Available
998K64KOfficial price
Input$0.30/1MOutput$1.50/1M
Verified price— Discount
—
—
qwen3.8-2.4t-a95bJSON modePrompt CacheTool useSupports prompt caching
Available
992K128KOfficial price
Input$2.00/1MOutput$6.00/1M
Verified price— Discount
—
—
qwen3.8-27bJSON modePrompt CacheTool useVisionSupports prompt caching
Available
992K128KOfficial price
Input$0.50/1MOutput$3.00/1M
Verified price— Discount
—
—
qwen3.8-flashJSON modePrompt CacheTool useVisionSupports prompt caching
Available
992K128KOfficial price
Input$0.15/1MOutput$0.47/1M
Verified price— Discount
—
—
qwen3.8-maxJSON modePrompt CacheTool useVisionSupports prompt caching
Available
992K128KOfficial price
Input$2.00/1MOutput$6.00/1M
Verified price— Discount
—
—
qwen3.8-omni-flashPrompt CacheReasoningTool useVisionSupports prompt caching
Available
1M—Official price
Input$0.15/1MOutput$0.47/1M
Verified price— Discount
—
—
qwen3.6-27bTool useVision
Available
128K32KOfficial price
Input$0.60/1MOutput$3.60/1M
Verified price— Discount
—
—
qwen-flashPrompt CacheReasoningSupports prompt caching
Available
998K32KOfficial price
Input$0.05/1MOutput$0.40/1M
Verified price— Discount
—
—
qwen-plusPrompt CacheSupports prompt caching
Available
998K32KOfficial price
Input$0.40/1MOutput$1.20/1M
Verified price— Discount
—
—
qwen3.5-flashPrompt CacheSupports prompt caching
Available
992K64KOfficial price
Input$0.10/1MOutput$0.40/1M
Verified price— Discount
—
—
qwen3.5-plusPrompt CacheSupports prompt caching
Available
992K64KOfficial price
Input$0.40/1MOutput$2.40/1M
Verified price— Discount
—
—
qwen3.7-maxPrompt CacheSupports prompt caching
Available
992K64KOfficial price
Input$2.50/1MOutput$7.50/1M
Verified price— Discount
—
—
qwen3.7-plusPrompt CacheReasoningSupports prompt caching
Available
992K64KOfficial price
Input$0.40/1MOutput$1.60/1M
Verified price— Discount
—
—
qwen3-vl-plusPrompt CacheVisionSupports prompt caching
Available
260K32KOfficial price
Input$0.20/1MOutput$1.60/1M
Verified price— Discount
—
—
qwen-doc-turboPrompt CacheSupports prompt caching
Available
254K8KOfficial price
Input$0.087/1MOutput$0.144/1M
Verified price— Discount
—
—
qwen-plus-characterPrompt CacheSupports prompt caching
Available
32K4KOfficial price
Input$0.50/1MOutput$1.40/1M
Verified price— Discount
—
—
qwen-maxPrompt CacheSupports prompt caching
Available
31K8KOfficial price
Input$1.60/1MOutput$6.40/1M
Verified price— Discount
—
—
qwen-flash-characterPrompt CacheSupports prompt caching
Available
8K4KOfficial price
Input$0.05/1MOutput$0.40/1M
Verified price— Discount
—
—
qwen3.5-27b
Available
260K64KOfficial price
Input$0.30/1MOutput$2.40/1M
Verified price— Discount
—
—
qwen3.5-omni-flashVision
Available
197K64KOfficial price
Input$0.40/1MOutput$2.20/1M
Verified price— Discount
—
—
qwen3.5-omni-plusVision
Available
197K64KOfficial price
Input$1.40/1MOutput$8.30/1M
Verified price— Discount
—
—
qwen3-omni-flashVision
Available
49K16KOfficial price
Input$0.43/1MOutput$1.66/1M
Verified price— Discount
—
—
qwen3.5-ocrVision
Available
49K16KOfficial price
Input$0.069/1MOutput$0.275/1M
Verified price— Discount
—
—
qwen-vl-ocrVision
Available
30K8KOfficial price
Input$0.07/1MOutput$0.16/1M
Verified price— Discount
—
—
1 / 3

All model series

6 series

Qwen 3 / QwQ

Alibaba Cloud
ChatRerank+2

Auto from $0.10 · per 1M tokens

12 modelsOpen series

Qwen

Alibaba Cloud
Chat

Auto from $0.0294 · per 1M tokens

9 modelsOpen series

Qwen Image

Alibaba Cloud
Image

Auto pricing units vary by model

8 modelsOpen series

Wan

Alibaba Cloud
ImageVideo

Auto pricing units vary by model

7 modelsOpen series

Qwen Embedding

Alibaba Cloud
EmbeddingVision

Auto from $0.0184 · per 1M tokens

5 modelsOpen series

Qwen Omni

Alibaba Cloud
ChatAudio+3

Auto from $0.15 · per 1M tokens

4 modelsOpen series